2022 Winner (Student’s Choice): ARIN-561

Target Audience: General Audience

Company: USC Institute of Creative Technologies

Description: ARIN-561 is an educational game designed to teach High School students AI concepts, & prompt them to apply math and problem-solving skills.

Skills and Ideas Taught: Classical search algorithms

Goal: The game aims to help students gain exposure to AI algorithms and connect AI to the math subjects students learn in the classroom, through AI problem-solving in a game environment.
Activities in the game aim to achieve target three audiences: students who will be AI end-users and use AI technology at workplaces, students who will be AI implementer and take existing AI technology to apply cross the society and economy, and students who will be AI researchers and advance AI algorithms.

The game also focuses on achieving three goals for these audiences. The first goal of ARIN-561 is for
students to understand how AI algorithms are used to solve problems in the real world. We take the approach of designing AI problem-solving in the game that mirrors real-world AI applications. For example, while ARIN-561 is set on an alien planet, the problems of route-planning on a map and cracking a computer password using search algorithms, are analogous of those in real-word planet earth.
The second goal is for students to learn how to weight the strengths and weaknesses of different AI algorithms in order to choose between them when attempting to use AI to solve a problem. In ARIN-561, each new AI algorithm is introduced as excelling at a task that previous algorithms are not as suitable for. As the students progress through the game, further comparisons between the AI algorithms are prompted, pushing the students to take more agency in deciding which one is appropriate for the task at hand. The third goal is for the students to learn somewhat in-depth how each AI algorithm works, which is achieved through the difficulty progression of the game-play. For each search algorithm, for example, the students are first provided with a tutorial task that teaches them how the algorithm works and walks them through the task step by step. Subsequently, the students are presented with a transfer problem from a domain different than the tutorial that requires the students to use the algorithms they have learned through the tutorial task. Students are provided with less tutorial support during this task and need to apply internalized understanding of how the algorithms they have learned work.

Primary Audience: High School Students

Assessment Approach: In the game, students have to demonstrate their understanding of the key concepts by solving AI problems themselves. For example, after being guided through the initial expansion of a search tree, students have to continue expanding the search tree following the
same algorithm. There are also quizzes inside the game for students’ self-checks of their understanding of the concepts just discussed. The game also employs stealth assessment through an assessment game at the end of the game. In the assessment level, students have to apply what they have learned in the game to solve similar AI problems. The research team also designed pre-and post-surveys to assess AI knowledge gained for pilot testing for the target population.

Game Engine: Unity

Operating System: Windows 10